シャドーイング練習: Prompt engineering - Introduction - 動画で英語スピーキングを学ぶ
練習モードを選ぶ
各モードは全画面の練習ルームで開きます。
68 文
文が短すぎたり長すぎる場合は、Editをタップして調整してください。
1
Welcome to this course on ChatGPT problem engineering for developers.
2
I'm thrilled to have with me Iza Fulford to teach this along with me.
3
She is a member of the technical staff of OpenAI and had built the popular ChatGPT retrieval plugin.
4
And a large part of work has been teaching people how to use OEM or large language model technology in products.
5
She's also contributed to the OpenAI cookbook that teaches people prompting.
6
So thrilled to have you with you.
7
And I'm thrilled to be here and share some prompting best practices with you all.
8
I'm not sure.
9
So there's been a lot of material on the internet for prompting,
10
with articles like "30 Prompts Everyone Has to Know" A lot of that has been focused on the ChatGPT web user interface,
11
which many people are using to do specific and often one -off tasks.
12
I think the power of LOM's large language models as a developer too, that is using API calls to LOMs to quickly build software applications.
13
I think that is still very underappreciated.
14
In fact, my team at AI Fund, which is a sister company to deep learning AI,
15
has been working with many startups on applying these technologies to many different applications.
16
It's been exciting to see what LOM APIs can enable developers to very quickly build.
17
So in this course, we'll share with you some of the possibilities for what you can do, as well as best practices for how you can do them.
18
There's a lot of material to cover.
19
First, you'll learn certain prompting best practices for software development.
20
Then we'll cover some common use cases, summarising, inferring, transforming, expanding.
21
And then you'll build a chatbot using an LLM.
22
Thank you.
23
We hope that this will spark your imagination about new applications that you can build.
24
So in the development of large language models or LLMs, there have been broadly two types of LLMs,
25
which I'm going to refer to as base LLMs and instruction -tuned LLMs.
26
So base LLM has been trained to predict the next word, based on text training data, often trained on large amount of data from the internet and other sources,
27
to figure out what's the next most likely word to follow.
28
So for example, if you were to prompt this, once upon a time there was a unicorn, it may complete this, that is, it may predict the next several words are,
29
that live in the magical forest of all unicorn friends.
30
But if you were to prompt us with what is the capital of France, then based on what articles on the internet might have,
31
it's quite possible that the base LM will complete this with, what is France's largest city, what is France's population and so on.
32
Because articles on the internet could quite plausibly be lists of quiz questions about the country of France.
33
Thank you.
34
In contrast, an instruction tuned LLM, which is where a lot of momentum of LLM research and practice has been going,
35
An instruction team has been trained to follow instructions.
36
So if you were to ask it, what is the capital of France is much more likely to output something like the capital of France is Paris
37
So the way that instruction -tuned OOMs are typically trained is, you start off with a base OOM that's been trained on a huge amount of text data,
38
and further train it, further fine tune it with inputs and outputs that are instructions and good attempts to follow those instructions.
39
And then often further refine using a technique called RLHF, reinforcement learning from human feedback,
40
to make the system better able to be helpful and follow instructions.
41
Because instruction TNLMs have been trained to be helpful, honest, and harmless.
42
So for example, they're less likely to output problematic texts, such as toxic outputs compared to base LLM.
43
a lot of the practical usage scenarios have been shifting toward instruction to,
44
you know, Some of the best practices you find on the internet may be more suited for a base LLM, but for most practical applications today,
45
we would recommend most people instead focus on instruction tuned LLMs, which are easier to use.
46
And also because of the work of OpenAI and other LLM companies becoming safer and more aligned.
47
So this course will focus on best practices for instruction to neural arms
48
which is what we recommend you use for most of your applications.
49
Before moving on, I just want to acknowledge the team from OpenAI
50
and DeepLearn .AI that had contributed to the materials that Ysia and I will be presenting.
51
I'm very grateful to Andrew Main, Joe Palermo, Boris Power, Ted Sanders, and Lillian Wang from OpenAI.
52
They were very involved with us brainstorming materials, vetting the materials to put together.
53
the curriculum for this short course.
54
And I'm also grateful on the deep learning side for the work of Jeff Lodwick, Eddie Hsu and Tommy Nelson.
55
So when you use an instruction tuned LLM, think of giving instructions to another person.
56
Say someone that's smart but doesn't know the specifics of your task.
57
So when an LM doesn't work, sometimes it's because the instructions weren't clear enough.
58
For example, if you were to say, "Please write me something about Alan Turing." Well, In addition to that, it can be helpful to be clear about whether you want
59
the text to focus on his scientific work or his personal life or his role in history or something else.
60
And if you specify what you want the tone of the text to be, should it take on the tone like a professional journalist would write?
61
Or is it more of a casual note
62
that you dash off to a friend that holds the OM generate what you want.
63
And of course, if you picture yourself asking, say a fresh college graduate to carry out this task for you,
64
if you can even specify what you want snippets of texts
65
they should read in advance to write this text about Alan Turing, then that even better sets up that fresh college grad for success to carry out this task for you.
66
So in the next video, you see examples of how to be clear and specific, which is an important principle of prompting LOMs.
67
And you also learn from Ezer a second principle of prompting, that is giving LDLM time to think.
68
So with that, let's go on to the next video.
アプリをダウンロード
流暢に話すために必要なすべて
AI発音採点文ごとに採点
IPA練習すべての音をマスター
単語学習自分の単語帳を作る
単語ゲーム遊びながら覚える
同じチャンネル
FOR YOU
おすすめ動画
C13
20 文
Is prompt engineering dead? Advice on optimizing AI interactions | Amazon Web Services
Business EnglishUniversity StudentsWorking Adults
C15
270 文
Transformers, the tech behind LLMs | Deep Learning Chapter 5
American AccentBusiness EnglishUniversity StudentsWorking Adults
C131
201 文
Improve Your English Listening & Speaking Fast | English Shadowing Practice B2 C1
Business EnglishDaily ConversationUniversity Students
C12
339 文
Easy Migration from Postgres to Databricks Lakebase
Business EnglishUniversity StudentsWorking Adults
C13
273 文
mattpocock/skills: A complete AI Coding workflow, end-to-end
British AccentBusiness EnglishUniversity StudentsWorking Adults
C13
43 文
P1 机器学习的应用【2024公认最好的 | 吴恩达机器学习 | 教程 | Machine Learning Specialization(超爽中英!)】
Business EnglishUniversity StudentsWorking Adults
C112
25 文
Introducing the Agents API
Business EnglishUniversity StudentsWorking Adults
C12
145 文
Most devs don't understand how LLM tokens work
British AccentBusiness EnglishUniversity StudentsWorking Adults
C16
10 文
What's new in Google Cloud in less than 1 minute
Business EnglishUniversity StudentsWorking Adults
C12
241 文
AI Concepts Every Product Manager Should Know in 25 Minutes | Crash Course
Business EnglishUniversity StudentsWorking Adults
C11
124 文
How to Make Anything - Learn to Think Like an Engineer
Business EnglishUniversity StudentsWorking Adults
C12
12 文
A Return to Code
Business EnglishUniversity StudentsWorking Adults
このビデオで話す練習をする理由は？
このビデオは、開発者向けのプロンプトエンジニアリングに関する内容で、特に大規模言語モデル（LLM）の使用方法について学ぶことができます。英語を話す練習をする中で、このような技術的な話を触れることで、専門的な語彙と表現を学ぶことができるのは大きな利点です。具体的な事例を通じて知識を得ることで、自信を持って英語でのコミュニケーションを図ることができます。さらに、英語の発音を良くするための練習としても有効です。特に、IELTSスピーキング対策として、このテーマに関連する語彙を使って、一段階上の英会話力を目指しましょう。
文法と表現のコンテキスト
- 基礎LLM（Base LLM） - この用語は、次に来る単語を予測するモデルを指します。文脈に応じて大切な概念を理解するために、正しい文法構造を身につけましょう。
- 指示調整LLM（Instruction-tuned LLM） - 指示に従うように訓練されたモデルです。ここでの「従う」という表現は、英語の命令文を学ぶ際に役立ちます。
- 人間のフィードバックからの強化学習（RLHF） - 技術者たちはこのプロセスを通じて、モデルがどのように向上するかを分析しています。これは、高度な英語運用能力が求められる場面で非常に役立つ文法ポイントです。
一般的な発音の罠
このビデオには、特に発音が難しい単語やフレーズがいくつかあります。例えば、“prompting”や“instruct” は、非英語話者にとって発音が難しい場合があります。また、“language model” のような複雑なフレーズも、正しいアクセントに注意が必要です。これらの単語を正確に発音することで、会話の流暢さが向上し、英語スピーキング練習の効果が高まります。
これらのポイントを意識しながら、shadowspeakまたはshadow speakのような影響を取り入れることで、よりスムーズな会話のスキルを磨くことができます。リスニング力と発音力を高めるための素晴らしい練習法となるでしょう。
この動画の文法
話し手がよく使っている文型を、動画の実際の表現とともに紹介します。
| 文型 | 動画での表現 |
|---|---|
| 現在完了進行形 have/has been + -ing — 以前に始まり今も続いている動作 | has been teaching · has been working · has been going |
| 現在完了形 have/has + 過去分詞 — 過去の出来事が今も関係している | there's been · has been · have been |
| 受動態 be + 過去分詞 — 誰がするかより、何が起きるかに焦点を当てる | has been trained · are typically trained · have been trained |
| 関係詞節 who / which + 節 — 人や物について情報を加える | Fund, which is · LLM, which is · LLMs, which are |
シャドーイングとは？英語上達に効果的な理由
シャドーイング（Shadowing）は、もともとプロの通訳者養成プログラムで開発された言語学習法で、多言語習得者として知られるDr. Alexander Arguelles によって広く普及されました。方法はシンプルですが非常に効果的：ネイティブスピーカーの英語を聞きながら、1〜2秒の遅延で声に出してすぐに繰り返す——まるで「影（shadow）」のように話者を追いかけます。文法ドリルや受動的なリスニングと異なり、シャドーイングは脳と口の筋肉が同時にリアルタイムで英語を処理・再現することを強制します。研究により、発音精度、抑揚、リズム、連音、リスニング力、そして会話の流暢さが大幅に向上することが確認されています。IELTSスピーキング対策や自然な英語コミュニケーションを目指す方に特におすすめです。